© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 40549
    Prev
    Next
    INDEX
    Explanations

    occurrences related to comparisons or quantities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    393
    +0.17
    0.7%
    447
    +0.13
    0.6%
    36
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.17
    0.24
    159
    +0.13
    0.13
    52
    +0.12
    0.11
    Negative Logits
    amiya
    -0.64
    heter
    -0.60
     apartheid
    -0.60
     ende
    -0.59
     annex
    -0.58
    ilial
    -0.58
     endeavour
    -0.57
     Measures
    -0.57
     Afric
    -0.57
    erness
    -0.57
    POSITIVE LOGITS
     foothold
    1.03
     traction
    1.02
    chy
    0.85
     mileage
    0.81
     glimpse
    0.81
    hold
    0.77
    started
    0.76
     thumbs
    0.72
    IFIED
    0.72
     firsthand
    0.72
    Activations Density 8.733%

    No Known Activations